Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    age, 3, corners

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    of
    0.33
    за
    0.33
     obsession
    0.29
     काळात
    0.29
    사
    0.29
    reliance
    0.29
     სახელმწიფ
    0.29
     пытается
    0.28
    EXCLUSIVE
    0.28
     wants
    0.28
    POSITIVE LOGITS
     cheerful
    0.33
     agradable
    0.32
     Blueberry
    0.32
     blueberries
    0.31
     Saturday
    0.31
     fluores
    0.31
     pleasantly
    0.31
     cheery
    0.31
     angene
    0.30
     agréable
    0.30
    Act Density 0.000%

    No Known Activations